CN103640532A - Pedestrian anti-collision early warning method based on recognition of braking and accelerating intention of driver - Google Patents
Pedestrian anti-collision early warning method based on recognition of braking and accelerating intention of driver Download PDFInfo
- Publication number
- CN103640532A CN103640532A CN201310640000.3A CN201310640000A CN103640532A CN 103640532 A CN103640532 A CN 103640532A CN 201310640000 A CN201310640000 A CN 201310640000A CN 103640532 A CN103640532 A CN 103640532A
- Authority
- CN
- China
- Prior art keywords
- data
- signal
- hidden markov
- braking
- intention
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Regulating Braking Force (AREA)
- Traffic Control Systems (AREA)
- Auxiliary Drives, Propulsion Controls, And Safety Devices (AREA)
Abstract
The invention discloses a pedestrian anti-collision early warning method based on recognition of the braking and accelerating intention of a driver. The method comprises the following steps: i, experimental data are collected for first-time off-line training of a hidden Markov model (HMM); ii, experimental data are collected for second-time off-line training of the HMM; iii, a data signal about the intention of the driver to avoid collisions with pedestrians is recognized; iv, data analysis is conducted in combination with an infrared human body induction data signal after the data signal about the intention of the driver to avoid collisions with the pedestrians is recognized, and different types of early warning processing are conducted. According to the pedestrian anti-collision early warning method based on recognition of the braking and accelerating intention of the driver, the pedestrians and vehicles serve as a system for studies, a corresponding early warning is given to the driver by means of analyzing the manipulative behavior and strategy which the driver may take when the pedestrians are in front of a car which the driver is driving and judging whether a risk exists according to the driving behavior and intention of the driver, and the early warning is given when the driver conducts wrong driving operation, for example, the driver treads on an accelerator pedal by mistake. As a result, the safety of the pedestrians is effectively protected, and the active safety performance of the car is improved.
Description
Technical field
The present invention relates to automobile active safety field, particularly a kind of based on chaufeur braking and the pedestrian's anticollision method for early warning that accelerates intention identification.
Background technology
In road traffic accident, pedestrian is the maximum colony that is injured often, and automobile and pedestrian to bump be one of major accident type.According to U.S. expressway safety Public Roads Administration statistics, the whole America in 2011, because traffic accident causes 6.9 ten thousand pedestrians injured, accounts for 3% of total number of injured people; Cause 4432 pedestrian's death, account for 14% of total death toll.In the road traffic accident of European Union, pedestrian's dead data are 9 times of passenger, and cyclist's dead data are 8 times of passenger.Within 2010, China is 16281 people because traffic accident causes the number of pedestrian's death, and number of injured people is 44629, accounts for respectively 25% and 18% of sum.At present; pedestrian protecting is by global common concern; aspect vehicle passive safety, formulate strict crash standards and pedestrian protecting rules; aspect automobile active safety by sensor technology perception the place ahead pedestrian and judge its precarious position; the in time alerting driver vehicle danger that may bump with the pedestrian in the place ahead, realizes active safety early warning.
Research to driving behavior at present, mainly concentrate on the detection of some dangerous driving behaviors and supervision, do not utilize environmental information to consider driving behavior and the intention of chaufeur, ignore the intention of chaufeur and the key effect that variation tendency plays in active safety control thereof, easily to the estimation that makes mistake of current road hazard situation.The present invention intends according to pedestrian detection result; in conjunction with travel condition of vehicle information and ambient condition information; use hidden markov model to carry out identification and prediction to chaufeur driving behavior and intention; analyze acceleration that chaufeur may take when running into vehicle front and have pedestrian by or stopping-down with manipulative behavior and strategies such as collision prevention pedestrians; and whether dangerous according to driving behavior and intention; chaufeur and the place ahead pedestrian are carried out to corresponding early warning, effectively protect pedestrian's safe, the active safety energy that improves automobile.
Summary of the invention
Defect in view of prior art existence; the object of the invention is to provide a kind of based on chaufeur braking and the pedestrian's anticollision method for early warning that accelerates intention identification; manipulative behavior and the strategy that by analyzing chaufeur, when running into vehicle front and have pedestrian, may take; and judge whether dangerous according to driving behavior and intention; chaufeur is carried out to corresponding early warning; wrong chaufeur driver behavior, such as early warning is carried out in the operation of error stepping on accelerator pedal, is effectively protected to pedestrian's safe, the active safety performance that improves automobile.
To achieve these goals, technical scheme of the present invention:
Based on chaufeur braking and the pedestrian's anticollision method for early warning that accelerates intention identification, comprise the steps:
I, collection observed data carry out an off-line training of hidden Markov HMM model:
For chaufeur, be the driving behavior that collision prevention pedestrian may take, gather observed data, described observed data comprises brake pedal force data, brake pedal displacement data, Das Gaspedal run-length data and vehicle speed data; After the long section observed data staging treating gathering, brake pedal force data, brake pedal displacement data, Das Gaspedal run-length data are input in braking and acceleration hidden Markov HMM model, vehicle speed data is input in velocity stages module; Braking with accelerate in Hidden Markov HMM model, build normal loose throttle, fast accelerator releasing, throttle keeps, step on the throttle, normally step on braking, fast step on braking, braking maintenance, take-off the brake and pedal attonity totally 9 about braking and multidimensional Gauss's hidden Markov HMM models of acceleration; Application Baum-Welch algorithm, carries out off-line training, each model parameter of iteration optimization to described 9 multidimensional Gauss Hidden Markov HMM models; The vehicle speed signal of same time period is pressed to Grade numbers, be input to velocity stages module;
II, collection observed data carry out the secondary off-line training of Hidden Markov HMM model: for chaufeur, be the driving behavior that collision prevention pedestrian may take, gather observed data, described observed data comprises brake pedal force data, brake pedal displacement data, Das Gaspedal run-length data and vehicle speed data; Brake pedal force data, brake pedal displacement data, Das Gaspedal run-length data are input to braking again and accelerate and, in hidden Markov HMM model, vehicle speed data is input in velocity stages module again; Application Forward-Backward algorithm calculates respectively the driving behavior observed data that newly collects with respect to the likelihood score of 9 driving behavior multidimensional Gauss Hidden Markov HMM models described in step I, selects the model of likelihood score maximum as chaufeur driving behavior identification result; And the two-dimentional driving behavior identification result string-braking of this Hidden Markov HMM model and acceleration identification result string and speed of a motor vehicle identification result string, observation sequence as driver intention identification hidden Markov HMM model, chaufeur collision prevention pedestrian is intended to identification HMM and carries out off-line training and optimization, obtain 2 chaufeur collision prevention pedestrians and be intended to Hidden Markov HMM model: accelerate Hidden Markov HMM model and stopping-down Hidden Markov HMM model;
III, pick out chaufeur collision prevention pedestrian and be intended to data-signal: by the brake pedal force sensor signals of Real-time Collection, brake pedal displacement transducer signal, Das Gaspedal stroke sensor signal is input to braking and accelerates in Hidden Markov HMM model, car speed sensor signal is input in velocity stages module, 9 driving behavior multidimensional Gauss Hidden Markov HMM models are carried out to off-line training and optimization, pick out driver's operation, obtain the two-dimentional identification result string-braking and acceleration identification result string and speed of a motor vehicle identification result string of driving behavior Hidden Markov HMM model, form after observation sequence string, send into 2 driver intention identification Hidden Markov HMM models, application Forward-Backward algorithm, calculate respectively the possibility that 2 Multidimensional Discrete Hidden Markov HMM models produce this observation sequence, select the model of likelihood score maximum as driving intention data-signal,
IV, pick out chaufeur collision prevention pedestrian and be intended in conjunction with infrared human body induction data-signal, carry out data analysis after data-signal, and make different early warning and process: the human inductor in automotive front setting based on infrared technology, for Real-time Collection human body sensing data-signal; In automobile mounted system, be provided for carrying out real-time data analysis and controlling the central processing unit that aud. snl. alarming device carries out early warning according to human body sensing data-signal and driving intention data-signal.
Described data analysis process comprises: if central processing unit analyzes human body sensing data-signal result, be that the place ahead does not exist pedestrian, no matter which kind of result driving intention data-signal is, central processing unit is not all sent energizing signal control aud. snl. alarming device and carried out early warning; If it is that the place ahead is while existing pedestrian and driving intention data-signal to be stopping-down intention signal that central processing unit analyzes human body sensing data-signal result; Central processing unit is not sent energizing signal control aud. snl. alarming device and is carried out early warning; If it is that the place ahead exists pedestrian and driving intention data-signal for accelerating intention signal that central processing unit analyzes human body sensing data-signal result; be that chaufeur is while can error stepping on accelerator pedal accelerating to pass through; central processing unit is sent energizing signal control aud. snl. alarming device and is carried out early warning, thereby reaches the object that chaufeur can make a response to protect pedestrian in time.
Compared with prior art, beneficial effect of the present invention:
The present invention studies pedestrian, vehicle as a system; the chaufeur braking and acceleration intention discrimination method of the early warning of a kind of pedestrian's of being applied to anticollision are provided; manipulative behavior and the strategy that by analyzing chaufeur, when running into vehicle front and have pedestrian, may take; and judge whether dangerous according to driving behavior and intention; chaufeur is carried out to corresponding early warning; wrong chaufeur driver behavior, such as early warning is carried out in the operation of error stepping on accelerator pedal, is effectively protected to pedestrian's safe, the active safety energy that improves automobile.
Accompanying drawing explanation
Fig. 1 the present invention is based on chaufeur braking and the pedestrian's anticollision method for early warning General layout Plan block diagram that accelerates intention identification.
Fig. 2 the present invention is based on chaufeur braking and the HMM model structure of accelerating pedestrian's anticollision method for early warning of intention identification.
Fig. 3 the present invention is based on chaufeur braking and the training process of HMM model that accelerates pedestrian's anticollision method for early warning of intention identification.
Fig. 4 the present invention is based on chaufeur braking and the diagram of circuit that accelerates pedestrian's anticollision method for early warning of intention identification.
In figure: 1, human inductor, 2, brake-pedal-travel sensor, 3, brake pedal force sensor, 4, Das Gaspedal stroke sensor, 5, car speed sensor, 6, HMM module, 7, central processing unit, 8, aud. snl. alarming device.
The specific embodiment
In order to make object of the present invention, technical scheme and advantage clearer, below in conjunction with accompanying drawing, the present invention is further elaborated.
As shown in Figure 1, design philosophy of the present invention is narrated based on chaufeur braking and the pedestrian's anticollision method for early warning example that accelerates intention identification by one of framework, and this example comprises and is arranged on human inductor 1, HMM module 6, central processing unit 7, the aud. snl. alarming device 8 of automotive front and the vehicle information collecting device that is arranged on automotive interior; Described vehicle information collecting device comprises: brake-pedal-travel sensor 2, brake pedal force sensor 3, Das Gaspedal stroke sensor 4 and car speed sensor 5; Wherein said brake-pedal-travel sensor 2, brake pedal force sensor 3, Das Gaspedal stroke sensor 4, car speed sensor 5 are connected with HMM module 6 signals respectively; Described human inductor 1, HMM module 6 are connected with central processing unit 7 respectively with aud. snl. alarming device 8.
Wherein, described aud. snl. alarming device 8 adopts buzzer phone to carry out sounding.
Wherein, the collection of data realizes by vehicle information collecting device, described vehicle information collecting device comprises brake-pedal-travel sensor 2, brake pedal force sensor 3, Das Gaspedal stroke sensor 4, car speed sensor 5 is for the various driving behavior image data of chaufeur, and described data comprise brake pedal force, brake pedal displacement, Das Gaspedal stroke and the speed of a motor vehicle; The sensing data of collection is input in HMM module 6 and picks out driver intention; The human inductor based on infrared technology 1 that is positioned at automotive front is intended to data information transfer to central processing unit 7 by the chaufeur collision prevention pedestrian of the real time information collecting and 6 predictions of HMM module, it is micro controller system, the incoming signal of described central processing unit 7 is the human body sensing data-signal of human inductor output and the driving intention data-signal of driver intention identification double-layered hidden Markov HMM model module output, and its output signal is controlled buzzer phone and carried out sounding.
The related process of this method comprises that an off-line training, secondary off-line training and the hidden Markov HMM Model Distinguish based on actual driving behavior data acquisition construction of the hidden Markov HMM model based on test experiment data acquisition construction go out chaufeur collision prevention pedestrian and be intended to after data-signal, by micro controller system, carries out early warning processing.
Ability in view of the powerful statistical basis of Hidden Markov HMM model, modular modeling method and processing Dynamic Time Series, built Hidden Markov HMM model structure (described Hidden Markov HMM model comprises braking and accelerates Hidden Markov HMM model and velocity stages module) as shown in Figure 2, to characterize the driver's operation under chaufeur collision prevention pedestrian intention and respective intent, and the driving intention data-signal of the behavior taked of identification chaufeur collision prevention pedestrian.
(2.1), vehicle information collecting device is passed through in the collection of observed data, be brake-pedal-travel sensor 2, brake pedal force sensor 3, Das Gaspedal stroke sensor 4 and car speed sensor 5, for chaufeur, it is the possible driving behavior of taking of collision prevention pedestrian, gather observed data, comprise brake pedal force sensor data, brake pedal displacement pickup data, Das Gaspedal stroke sensor data and car speed sensor data;
adoptingafter one long section observed data staging treating of collection, brake pedal force sensor data, brake pedal displacement pickup data, Das Gaspedal stroke sensor data are input to braking and accelerate Hidden Markov HMM model, car speed sensor data are input in velocity stages module;
(2.2), braking with accelerate in Hidden Markov HMM model, build normal loose throttle, fast accelerator releasing, throttle keeps, step on the throttle, normally step on braking, fast step on braking, braking maintenance, take-off the brake and pedal attonity totally 9 about braking and multidimensional Gauss's Hidden Markov HMM models of acceleration.Application Baum-Welch algorithm, carries out off-line training, the parameter of each model of iteration optimization to 9 multidimensional Gauss Hidden Markov HMM;
(2.3), in view of the observed data gathering is a long section observation sequence, need to carry out staging treating to it, therefore, pressing Grade numbers with the vehicle speed signal of time period, be input to velocity stages module.Described Grade numbers is, according to the size of speed, speed is carried out to classification numbering, for example: the size of speed is 60km/h, and the grade of speed is exactly 6.
(2.4), the two-dimentional driving behavior identification result string of the Hidden Markov HMM model obtaining (braking and acceleration identification result string and speed of a motor vehicle identification result string), observation sequence as driving intention identification Hidden Markov HMM model, chaufeur collision prevention pedestrian is intended to identification HMM and carries out off-line training and optimization, obtain 2 chaufeur collision prevention pedestrians and be intended to Hidden Markov HMM model: accelerate intention Hidden Markov HMM model and stopping-down intention Hidden Markov HMM model.
(2.5), by the brake pedal force sensor signals of Real-time Collection in actual driving situation, brake pedal displacement transducer signal, Das Gaspedal stroke sensor signal is input to braking and accelerates in Hidden Markov HMM model, car speed sensor signal is input in velocity stages module, with reference to step (2.1), (2.2), 9 multidimensional Gauss Hidden Markov HMM are carried out to off-line training and optimization, pick out driver's operation, obtain the two-dimentional identification result string (braking and acceleration and the speed of a motor vehicle) of driving behavior Hidden Markov HMM, form after observation sequence string, 2 chaufeur collision prevention pedestrians that send into step (2.4) are intended to Hidden Markov HMM model, application Forward-Backward algorithm, calculate respectively the possibility that 2 Multidimensional Discrete Hidden Markov HMM models produce this observation sequence, select the model of likelihood score maximum as driving intention data-signal,
As Fig. 3, patent of the present invention is applied to the chaufeur braking and the training process that accelerates the HMM of intention discrimination method of pedestrian's anticollision early warning, comprises the following steps:
(3.1), vehicle information collecting device is passed through in the collection of observed data, be brake-pedal-travel sensor, brake pedal force sensor, Das Gaspedal stroke sensor and car speed sensor, for chaufeur, it is the driving behavior that collision prevention pedestrian may take, gather observed data, comprise brake pedal force, brake pedal displacement, Das Gaspedal stroke and car speed sensor data; After the long section observed data staging treating gathering, brake pedal force, brake pedal displacement, Das Gaspedal stroke sensor data are input to braking and accelerate Hidden Markov HMM model, the speed of a motor vehicle is input in velocity stages module;
(3.2), braking with accelerate in Hidden Markov HMM model module, build normal loose throttle, fast accelerator releasing, throttle keeps, step on the throttle, normally step on braking, fast step on braking, braking maintenance, take-off the brake and pedal attonity totally 9 about braking and multidimensional Gauss's Hidden Markov HMM models of acceleration.Application Baum-Welch algorithm, carries out off-line training, the parameter of each model of iteration optimization to 9 multidimensional Gauss Hidden Markov HMM;
(3.3), in view of the observed data gathering is a long section observation sequence, need to carry out staging treating to it, therefore, pressing Grade numbers with the vehicle speed signal of time period, be input to velocity stages module.Described Grade numbers is, according to the size of speed, speed is carried out to classification numbering, for example: the size of speed is 60km/h, and the grade of speed is exactly 6.
(3.4), vehicle information collecting device is passed through in the collection of observed data, different driving intentions for chaufeur collision prevention pedestrian accelerate and stopping-down, gather observed data, comprise brake pedal force, brake pedal displacement, Das Gaspedal stroke and car speed sensor data;
(3.5), brake pedal force sensor data, brake pedal displacement pickup data, Das Gaspedal stroke sensor data be input to braking and accelerate, in Hidden Markov HMM model, car speed sensor data to be input in velocity stages module; Application Forward-Backward algorithm calculates respectively the driving behavior sensing data that newly collects with respect to the likelihood score of 9 driving behavior multidimensional Gauss Hidden Markov HMM models, selects the model of likelihood score maximum as chaufeur driving behavior identification result;
(3.6), the two-dimentional identification result string (braking and acceleration and the speed of a motor vehicle) of the driving behavior Hidden Markov HMM obtaining, as chaufeur collision prevention pedestrian, be intended to the observation sequence of identification Hidden Markov HMM model, chaufeur collision prevention pedestrian is intended to identification HMM and carries out off-line training and optimization, obtain 2 driver intention Hidden Markov HMM models: accelerate Hidden Markov HMM model and stopping-down Hidden Markov HMM model;
(3.7), by the brake pedal force sensor data of Real-time Collection, brake pedal displacement pickup data, Das Gaspedal stroke sensor signal is input to braking and accelerates in Hidden Markov HMM model, the speed of a motor vehicle is input in velocity stages module, with reference to step (1), (2), 9 multidimensional Gauss HMM are carried out to off-line training and optimization, pick out driver's operation, obtain the two-dimentional identification result string (braking and acceleration and the speed of a motor vehicle) of driving behavior Hidden Markov HMM, form after observation sequence string, send into 2 driver intention identification Hidden Markov HMM models, application Forward-Backward algorithm, calculate respectively the possibility that 2 driver intention Multidimensional Discrete Hidden Markov HMM models produce this observation sequence, select the model of likelihood score maximum as driver intention data.
As shown in Figure 4, vehicle information collecting device is passed through in the collection of data, be brake-pedal-travel sensor 2, brake pedal force sensor 3, Das Gaspedal stroke sensor 4 and car speed sensor 5, for chaufeur, it is the driving behavior that collision prevention pedestrian may take, image data, comprises brake pedal force, brake pedal displacement, Das Gaspedal stroke and the speed of a motor vehicle; The sensing data of collection is input in HMM module 6, picks out chaufeur collision prevention pedestrian and be intended to accelerate or stopping-down, chaufeur may error stepping on accelerator pedal accelerate by or stopping-down to hide pedestrian; The human inductor based on infrared technology 1 that is positioned at automotive front passes to central processing unit 7 by the driver intention information of the real time information collecting and 6 predictions of HMM module, it is micro controller system, central processing unit 7 picks out chaufeur collision prevention pedestrian and is intended in conjunction with described intent information and infrared human body induction data-signal, carry out data analysis after data-signal, and makes different early warning and process.Described data analysis process comprises: if central processing unit 7 analyzes human body sensing data-signal result, be that the place ahead does not exist pedestrian, no matter which kind of result driving intention data-signal is, central processing unit is not all sent energizing signal control aud. snl. alarming device 8 and carried out early warning; If it is that the place ahead is while existing pedestrian and driving intention data-signal to be stopping-down intention signal that central processing unit 7 analyzes human body sensing data-signal result; Central processing unit is not sent energizing signal control province tone signal alarming device 8 and is carried out early warning; If it is that the place ahead exists pedestrian and driving intention data-signal for accelerating intention signal that central processing unit 7 analyzes human body sensing data-signal result; be that chaufeur is while can error stepping on accelerator pedal accelerating to pass through; central processing unit 7 is sent energizing signal control aud. snl. alarming device 8 and is carried out early warning, thereby reaches the object that chaufeur can make a response to protect pedestrian in time.
The above; it is only the preferably specific embodiment of the present invention; but protection scope of the present invention is not limited to this; anyly be familiar with those skilled in the art in the technical scope that the present invention discloses; according to technical scheme of the present invention and inventive concept thereof, be equal to replacement or changed, within all should being encompassed in protection scope of the present invention.
Claims (2)
1. based on chaufeur braking and the pedestrian's anticollision method for early warning that accelerates intention identification, it is characterized in that: comprise the steps:
I, collection observed data carry out an off-line training of hidden Markov HMM model:
For chaufeur, be the driving behavior that collision prevention pedestrian may take, gather observed data, described observed data comprises brake pedal force data, brake pedal displacement data, Das Gaspedal run-length data and vehicle speed data; After the long section observed data staging treating gathering, brake pedal force data, brake pedal displacement data, Das Gaspedal run-length data are input in braking and acceleration hidden Markov HMM model, vehicle speed data is input in velocity stages module; Braking with accelerate in Hidden Markov HMM model, build normal loose throttle, fast accelerator releasing, throttle keeps, step on the throttle, normally step on braking, fast step on braking, braking maintenance, take-off the brake and pedal attonity totally 9 about braking and multidimensional Gauss's hidden Markov HMM models of acceleration; Application Baum-Welch algorithm, carries out off-line training, each model parameter of iteration optimization to described 9 multidimensional Gauss Hidden Markov HMM models; The vehicle speed signal of same time period is pressed to Grade numbers, be input to velocity stages module;
II, collection observed data carry out the secondary off-line training of Hidden Markov HMM model: for chaufeur, be the driving behavior that collision prevention pedestrian may take, gather observed data, described observed data comprises brake pedal force data, brake pedal displacement data, Das Gaspedal run-length data and vehicle speed data; Brake pedal force data, brake pedal displacement data, Das Gaspedal run-length data are input to braking again and accelerate and, in hidden Markov HMM model, vehicle speed data is input in velocity stages module again; Application Forward-Backward algorithm calculates respectively the driving behavior observed data that newly collects with respect to the likelihood score of 9 driving behavior multidimensional Gauss Hidden Markov HMM models described in step I, selects the model of likelihood score maximum as chaufeur driving behavior identification result; And the two-dimentional driving behavior identification result string-braking of this Hidden Markov HMM model and acceleration identification result string and speed of a motor vehicle identification result string, observation sequence as driver intention identification hidden Markov HMM model, chaufeur collision prevention pedestrian is intended to identification HMM and carries out off-line training and optimization, obtain 2 chaufeur collision prevention pedestrians and be intended to Hidden Markov HMM model: accelerate Hidden Markov HMM model and stopping-down Hidden Markov HMM model;
III, pick out chaufeur collision prevention pedestrian and be intended to data-signal: by the brake pedal force sensor signals of Real-time Collection, brake pedal displacement transducer signal, Das Gaspedal stroke sensor signal is input to braking and accelerates in Hidden Markov HMM model, car speed sensor signal is input in velocity stages module, 9 driving behavior multidimensional Gauss Hidden Markov HMM models are carried out to off-line training and optimization, pick out driver's operation, obtain the two-dimentional identification result string-braking and acceleration identification result string and speed of a motor vehicle identification result string of driving behavior Hidden Markov HMM model, form after observation sequence string, send into 2 Hidden Markov HMM models of driver intention identification, application Forward-Backward algorithm, calculate respectively the possibility that 2 Multidimensional Discrete Hidden Markov HMM models produce this observation sequence, select the model of likelihood score maximum as driving intention data-signal,
IV, pick out chaufeur collision prevention pedestrian and be intended in conjunction with infrared human body induction data-signal, carry out data analysis after data-signal, and make different early warning and process: the human inductor in automotive front setting based on infrared technology, for Real-time Collection human body sensing data-signal; In automobile mounted system, be provided for carrying out real-time data analysis and controlling the central processing unit that aud. snl. alarming device carries out early warning according to human body sensing data-signal and driving intention data-signal.
2. according to claim 1 based on chaufeur braking and the pedestrian's anticollision method for early warning that accelerates intention identification, it is characterized in that: described data analysis process comprises: if central processing unit analyzes human body sensing data-signal result, be that the place ahead does not exist pedestrian, no matter which kind of result driving intention data-signal is, central processing unit is not all sent energizing signal control aud. snl. alarming device and carried out early warning; If it is that the place ahead is while existing pedestrian and driving intention data-signal to be stopping-down intention signal that central processing unit analyzes human body sensing data-signal result; Central processing unit is not sent energizing signal control aud. snl. alarming device and is carried out early warning; If it is that the place ahead exists pedestrian and driving intention data-signal for accelerating intention signal that central processing unit analyzes human body sensing data-signal result; be that chaufeur is while can error stepping on accelerator pedal accelerating to pass through; central processing unit is sent energizing signal control aud. snl. alarming device and is carried out early warning, thereby reaches the object that chaufeur can make a response to protect pedestrian in time.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310640000.3A CN103640532B (en) | 2013-11-29 | 2013-11-29 | The pedestrian anti-collision method for early warning of identification is intended to based on chaufeur braking and acceleration |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310640000.3A CN103640532B (en) | 2013-11-29 | 2013-11-29 | The pedestrian anti-collision method for early warning of identification is intended to based on chaufeur braking and acceleration |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103640532A true CN103640532A (en) | 2014-03-19 |
| CN103640532B CN103640532B (en) | 2015-08-26 |
Family
ID=50245877
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310640000.3A Expired - Fee Related CN103640532B (en) | 2013-11-29 | 2013-11-29 | The pedestrian anti-collision method for early warning of identification is intended to based on chaufeur braking and acceleration |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103640532B (en) |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104217615A (en) * | 2014-09-16 | 2014-12-17 | 武汉理工大学 | System and method for preventing pedestrians from collision based on vehicle-road cooperation |
| CN106023344A (en) * | 2016-06-06 | 2016-10-12 | 清华大学 | Driving style estimation method based on driving pattern transition probability |
| CN106383918A (en) * | 2016-11-17 | 2017-02-08 | 吉林大学 | System for distinguishing reasonability of emergency braking behavior and distinguishing method |
| CN106740864A (en) * | 2017-01-12 | 2017-05-31 | 北京交通大学 | A kind of driving behavior is intended to judge and Forecasting Methodology |
| CN106828503A (en) * | 2017-02-15 | 2017-06-13 | 武汉理工大学 | A kind of operator brake behavior and state real-time identification method |
| US10089880B2 (en) | 2016-11-08 | 2018-10-02 | International Business Machines Corporation | Warning driver of intent of others |
| CN109063642A (en) * | 2018-08-01 | 2018-12-21 | 广州大学 | The prediction technique and system that pedestrian based on HMM algorithm goes across the road |
| CN110386144A (en) * | 2019-06-19 | 2019-10-29 | 长安大学 | The GHMM/GGAP-RBF mixed model and discrimination method that a kind of pair of driver's braking intention is recognized |
| CN111267847A (en) * | 2020-02-11 | 2020-06-12 | 吉林大学 | Personalized self-adaptive cruise control system |
| CN111746555A (en) * | 2019-03-26 | 2020-10-09 | 通用汽车环球科技运作有限责任公司 | Identification and avoidance of collision behavior |
| CN112002126A (en) * | 2020-09-02 | 2020-11-27 | 中国科学技术大学 | Method and system for predicting long-term trajectory of vehicle in complex scene |
| CN112242069A (en) * | 2019-07-17 | 2021-01-19 | 华为技术有限公司 | Method and device for determining vehicle speed |
| CN112560995A (en) * | 2020-12-26 | 2021-03-26 | 浙江天行健智能科技有限公司 | GM-HMM-based parking intention identification method |
| CN115131874A (en) * | 2022-06-29 | 2022-09-30 | 深圳市神州云海智能科技有限公司 | User behavior recognition prediction method and system and intelligent safety helmet |
| CN116340840A (en) * | 2023-02-15 | 2023-06-27 | 华中科技大学 | GA-PSO-HMM-based method for identifying driving intention |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201380848Y (en) * | 2008-12-31 | 2010-01-13 | 广州市品壹电器科技有限公司 | Incorrect-brake intelligent controlling and braking device monitored by laser or infrared ray |
| JP2010092115A (en) * | 2008-10-03 | 2010-04-22 | Honda Motor Co Ltd | Warning device of vehicle |
| CN101875348A (en) * | 2010-07-01 | 2010-11-03 | 浙江工业大学 | Device for preventing faulty operation for using accelerator as brake by mistake based on computer vision |
| CN103318181A (en) * | 2013-06-19 | 2013-09-25 | 电子科技大学 | Driver intention recognition method |
-
2013
- 2013-11-29 CN CN201310640000.3A patent/CN103640532B/en not_active Expired - Fee Related
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010092115A (en) * | 2008-10-03 | 2010-04-22 | Honda Motor Co Ltd | Warning device of vehicle |
| CN201380848Y (en) * | 2008-12-31 | 2010-01-13 | 广州市品壹电器科技有限公司 | Incorrect-brake intelligent controlling and braking device monitored by laser or infrared ray |
| CN101875348A (en) * | 2010-07-01 | 2010-11-03 | 浙江工业大学 | Device for preventing faulty operation for using accelerator as brake by mistake based on computer vision |
| CN103318181A (en) * | 2013-06-19 | 2013-09-25 | 电子科技大学 | Driver intention recognition method |
Non-Patent Citations (1)
| Title |
|---|
| 宗长富，王畅，何磊，郑宏宇，张泽星: "基于双层隐式马尔科夫模型的驾驶意图辨识", 《汽车工程》 * |
Cited By (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104217615A (en) * | 2014-09-16 | 2014-12-17 | 武汉理工大学 | System and method for preventing pedestrians from collision based on vehicle-road cooperation |
| CN106023344A (en) * | 2016-06-06 | 2016-10-12 | 清华大学 | Driving style estimation method based on driving pattern transition probability |
| CN106023344B (en) * | 2016-06-06 | 2019-04-05 | 清华大学 | Driving style estimation method based on driving mode transition probability |
| US10089880B2 (en) | 2016-11-08 | 2018-10-02 | International Business Machines Corporation | Warning driver of intent of others |
| US10360800B2 (en) | 2016-11-08 | 2019-07-23 | International Business Machines Corporation | Warning driver of intent of others |
| CN106383918A (en) * | 2016-11-17 | 2017-02-08 | 吉林大学 | System for distinguishing reasonability of emergency braking behavior and distinguishing method |
| CN106740864A (en) * | 2017-01-12 | 2017-05-31 | 北京交通大学 | A kind of driving behavior is intended to judge and Forecasting Methodology |
| CN106740864B (en) * | 2017-01-12 | 2019-03-19 | 北京交通大学 | A kind of driving behavior is intended to judgement and prediction technique |
| CN106828503A (en) * | 2017-02-15 | 2017-06-13 | 武汉理工大学 | A kind of operator brake behavior and state real-time identification method |
| CN109063642A (en) * | 2018-08-01 | 2018-12-21 | 广州大学 | The prediction technique and system that pedestrian based on HMM algorithm goes across the road |
| CN111746555A (en) * | 2019-03-26 | 2020-10-09 | 通用汽车环球科技运作有限责任公司 | Identification and avoidance of collision behavior |
| CN110386144A (en) * | 2019-06-19 | 2019-10-29 | 长安大学 | The GHMM/GGAP-RBF mixed model and discrimination method that a kind of pair of driver's braking intention is recognized |
| CN110386144B (en) * | 2019-06-19 | 2020-09-08 | 长安大学 | GHMM/GGAP-RBF hybrid model for identifying driver braking intention and identification method |
| CN112242069A (en) * | 2019-07-17 | 2021-01-19 | 华为技术有限公司 | Method and device for determining vehicle speed |
| CN112242069B (en) * | 2019-07-17 | 2021-10-01 | 华为技术有限公司 | Method and device for determining vehicle speed |
| US11273838B2 (en) | 2019-07-17 | 2022-03-15 | Huawei Technologies Co., Ltd. | Method and apparatus for determining vehicle speed |
| CN111267847A (en) * | 2020-02-11 | 2020-06-12 | 吉林大学 | Personalized self-adaptive cruise control system |
| CN111267847B (en) * | 2020-02-11 | 2021-08-17 | 吉林大学 | Personalized self-adaptive cruise control system |
| CN112002126A (en) * | 2020-09-02 | 2020-11-27 | 中国科学技术大学 | Method and system for predicting long-term trajectory of vehicle in complex scene |
| CN112560995A (en) * | 2020-12-26 | 2021-03-26 | 浙江天行健智能科技有限公司 | GM-HMM-based parking intention identification method |
| CN115131874A (en) * | 2022-06-29 | 2022-09-30 | 深圳市神州云海智能科技有限公司 | User behavior recognition prediction method and system and intelligent safety helmet |
| CN115131874B (en) * | 2022-06-29 | 2023-10-17 | 深圳市神州云海智能科技有限公司 | User behavior recognition prediction method, system and intelligent safety helmet |
| CN116340840A (en) * | 2023-02-15 | 2023-06-27 | 华中科技大学 | GA-PSO-HMM-based method for identifying driving intention |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103640532B (en) | 2015-08-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103640532B (en) | The pedestrian anti-collision method for early warning of identification is intended to based on chaufeur braking and acceleration | |
| CN106740864B (en) | A kind of driving behavior is intended to judgement and prediction technique | |
| CN105015548B (en) | A kind of longitudinal collision avoidance is reminded and follows integrated system and method automatically | |
| CN103531042B (en) | Based on the vehicle rear-end collision method for early warning of driver's type | |
| CN105599773B (en) | A kind of driver status suggestion device and its method based on moving attitude of vehicle | |
| CN109242251A (en) | Vehicular behavior safety detecting method, device, equipment and storage medium | |
| CN101470951B (en) | Vehicle security drive monitoring system | |
| CN110155046A (en) | Automatic emergency brake hierarchical control method and system | |
| CN110077398B (en) | Risk handling method for intelligent driving | |
| CN113635897B (en) | Safe driving early warning method based on risk field | |
| CN105679020A (en) | Driving behavior analysis device and method | |
| CN108263278A (en) | The pedestrian detection and pedestrian anti-collision device and method integrated based on sensor | |
| CN106240571B (en) | Driving behavior analysis method and apparatus | |
| CN112590801B (en) | Front collision early warning control method based on fatigue degree of driver | |
| CN110316198A (en) | A kind of safe-guard system and operation method for highway speed-raising | |
| CN107031553A (en) | A kind of tailgating-proof system and method for vehicle | |
| CN105070053A (en) | Intelligent traffic monitoring camera for identifying vehicle illegal movement modes | |
| CN110085042A (en) | A kind of vehicle drive early warning system and method based on information fusion | |
| CN102785660A (en) | Vehicle collision-proof early warning device | |
| CN106467057B (en) | The method, apparatus and system of lane departure warning | |
| CN109632330A (en) | A kind of the AEB system cyclist's crash tests device and its test method of low cost | |
| CN112874515A (en) | System and method for carrying out safety reminding on driving assistance system by using driving posture | |
| CN106383918A (en) | System for distinguishing reasonability of emergency braking behavior and distinguishing method | |
| CN201882025U (en) | Anti-collision device for automobile | |
| CN108230717A (en) | A kind of Intelligent traffic management systems |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20150826 Termination date: 20181129 |